How Popsa used Amazon Nova to inspire customers with personalised title suggestions
TL;DR
In this post, we share how we applied Amazon Bedrock and the Amazon Nova family of models to reimagine our Title Suggestion feature. By combining metadata, computer vision, and retrieval-augmented generative AI, we now automatically generate creative, brand-aligned titles and subtitles across 12 languages. Using the unified API of Amazon Bedrock, Anthropic's Claude 3 Haiku, and Amazon Nova Lite and Pro, we improved quality, reduced cost, and cut response times. This resulted in higher customer satisfaction, measurable uplifts in engagement and purchase rates, and over 5.5 million personalised titles generated in 2025.
Nauti's Take
Nauti finds the numbers compelling: 5.5 million personalised titles and measurable lifts in engagement show that a careful multi-model strategy on Bedrock can produce real business impact. The combination of metadata, computer vision and RAG is a solid blueprint for brand-consistent generation.
That said, the use case is narrow (photobook titles) and Bedrock lock-in makes future model swaps painful. Teams planning something similar should benchmark models for their own workload instead of copying the stack blindly.
Sources
